Improved rotational matching of sift and surf
Scale-Invariant Feature Transform(SIFT) and Speeded-Up Robust Feature(SURF) are common techniques used for extracting robust features that can be used to perform matching between different viewpoints of scenes. Both methods basically involve three main stages, which are feature extraction, orientati...
| Main Authors: | , , |
|---|---|
| Format: | Book Section |
| Published: |
SPIE
2012
|
| Subjects: |
| _version_ | 1796857460311457792 |
|---|---|
| author | Goh, Kian Mau Mohd. Mokji, Musa Syed Abu Bakar, Syed Abdul Rahman |
| author_facet | Goh, Kian Mau Mohd. Mokji, Musa Syed Abu Bakar, Syed Abdul Rahman |
| author_sort | Goh, Kian Mau |
| collection | ePrints |
| description | Scale-Invariant Feature Transform(SIFT) and Speeded-Up Robust Feature(SURF) are common techniques used for extracting robust features that can be used to perform matching between different viewpoints of scenes. Both methods basically involve three main stages, which are feature extraction, orientation assignment and feature descriptor extraction for matching. SURF is computation efficient compared to SIFT because the integral image is used for the convolutions to reduce computation time. However, both methods also do not focus much on the technique of matching. This paper introduces a method which can help to improve the rotational matching performance in term of accuracy by establishing a decision matrix and an approximated rotational angle within two corresponding images. The proposed method generally improved the matching rate around 10% to 20% in terms of accuracy. |
| first_indexed | 2024-03-05T18:58:07Z |
| format | Book Section |
| id | utm.eprints-35809 |
| institution | Universiti Teknologi Malaysia - ePrints |
| last_indexed | 2024-03-05T18:58:07Z |
| publishDate | 2012 |
| publisher | SPIE |
| record_format | dspace |
| spelling | utm.eprints-358092017-02-02T05:27:40Z http://eprints.utm.my/35809/ Improved rotational matching of sift and surf Goh, Kian Mau Mohd. Mokji, Musa Syed Abu Bakar, Syed Abdul Rahman Q Science Scale-Invariant Feature Transform(SIFT) and Speeded-Up Robust Feature(SURF) are common techniques used for extracting robust features that can be used to perform matching between different viewpoints of scenes. Both methods basically involve three main stages, which are feature extraction, orientation assignment and feature descriptor extraction for matching. SURF is computation efficient compared to SIFT because the integral image is used for the convolutions to reduce computation time. However, both methods also do not focus much on the technique of matching. This paper introduces a method which can help to improve the rotational matching performance in term of accuracy by establishing a decision matrix and an approximated rotational angle within two corresponding images. The proposed method generally improved the matching rate around 10% to 20% in terms of accuracy. SPIE 2012 Book Section PeerReviewed Goh, Kian Mau and Mohd. Mokji, Musa and Syed Abu Bakar, Syed Abdul Rahman (2012) Improved rotational matching of sift and surf. In: Fourth International Conference on Digital Image Processing (ICDIP 2012). SPIE, Bellingham, USA, pp. 1-6. ISBN 978-081948991-3 http://dx.doi.org/10.1117/12.953950 DOI:10.1117/12.953950 |
| spellingShingle | Q Science Goh, Kian Mau Mohd. Mokji, Musa Syed Abu Bakar, Syed Abdul Rahman Improved rotational matching of sift and surf |
| title | Improved rotational matching of sift and surf |
| title_full | Improved rotational matching of sift and surf |
| title_fullStr | Improved rotational matching of sift and surf |
| title_full_unstemmed | Improved rotational matching of sift and surf |
| title_short | Improved rotational matching of sift and surf |
| title_sort | improved rotational matching of sift and surf |
| topic | Q Science |
| work_keys_str_mv | AT gohkianmau improvedrotationalmatchingofsiftandsurf AT mohdmokjimusa improvedrotationalmatchingofsiftandsurf AT syedabubakarsyedabdulrahman improvedrotationalmatchingofsiftandsurf |